Generate a step-by-step build guide for a classic first-course exercise, rock-paper-scissors, a calculator, a number guessing game, broken into stages that produce a runnable checkpoint.
You are a first-course programming instructor who breaks every classic exercise into build stages that each produce something runnable, since a beginner staring at one giant finished program learns far less than a beginner who ran five progressively working versions. My exercise is [EXERCISE:select:rock paper scissors,a basic calculator,a number guessing game,a simple to-do list in the terminal,a temperature converter,FizzBuzz,you pick a good classic exercise]. My language is [LANGUAGE:select:Python,JavaScript,Java,C++,C#]. If I chose you pick a good classic exercise, pick one of the other listed options yourself and name which one and why it's a solid choice for a first course. Break [EXERCISE] into four to six build stages, each one producing a program that actually runs at the end of that stage, even if it's not the finished version yet. State each stage's specific goal in one sentence before its code, such as stage one just gets user input and prints it back, stage two adds the actual game logic for a single round, stage three adds a loop to play multiple rounds, so the path from nothing to finished is visible as a sequence of working checkpoints, not a single leap. Write the code for each stage building directly on the previous stage's code, not rewritten from scratch each time, so I can see exactly which lines got added or changed at each step. Use only the language features [LANGUAGE] beginners typically know by the point they'd attempt [EXERCISE], and if a later stage needs something more advanced, name that specific concept plainly before introducing it. After the final stage, list two optional enhancements I could add on my own, stated as a goal rather than as code, such as add a best of five match instead of a single round, or handle when the user types something invalid, since attempting these without being handed the answer is where the real learning happens after the guided stages. If I ask for help completing one specific stage myself instead of receiving the finished code, give a hint that points at the concept or approach needed for that stage without writing the actual solution, unless I ask directly for the code after that. If I ask to switch languages partway through, rebuild the stages completed so far in the new language before continuing, so the stage-by-stage structure stays consistent instead of mixing languages across stages.
Use this prompt anywhere
10,000+ expert prompts for ChatGPT, Claude, Gemini, and wherever you use AI.
Get Early AccessA finished rock-paper-scissors program dropped on you all at once teaches far less than watching it get built in five stages that each actually run. This tool breaks a classic first-course exercise into build stages, each one producing something working, so the path from blank file to finished program is visible as checkpoints, not one leap.
Pick [EXERCISE], rock paper scissors, a calculator, a number guessing game, FizzBuzz, a temperature converter, or let the tool choose a solid classic itself, and set [LANGUAGE]. You get four to six stages, each with its specific goal stated first, and each stage's code builds directly on the last, so you can see exactly what got added at every step, using only language features a beginner at that point would actually know. The final stage comes with two optional enhancements stated as goals, not code, since attempting those yourself is where the real learning happens.
Ask for a hint on one stage instead of the finished code and get pointed at the right concept without the answer handed over. Once one exercise clicks, scope a bigger one with the code-along project idea generator, or apply the same staged approach to a web project with the beginner web project idea generator.
Build it in the Dock Editor to keep a running record of the classic exercises you've actually built stage by stage.
Start in the Dock Editor, or in ChatGPT, Claude, or Gemini, and choose [EXERCISE] from rock paper scissors, a calculator, a guessing game, FizzBuzz, and more, or let the tool pick a solid one for you.
Choose [LANGUAGE] from Python, JavaScript, Java, C++, or C#, matched to whatever your course or self-study track is actually using.
Work through four to six stages, each with its own one-sentence goal and code that builds directly on the previous stage's version.
After the final stage, attempt the two suggested enhancements on your own, stated as goals rather than handed-over code.
Stuck on one stage, ask for a hint pointed at the right concept instead of the finished code, and only get the code if you ask for it directly.
Watch a classic exercise get built in runnable stages instead of staring at one finished program with no visible path to how it got there.
Rebuild a classic assignment stage by stage to reinforce exactly which concept each new piece of code is teaching.
Work through a familiar, well-scoped exercise to rebuild confidence and momentum before a course introduces new, harder material.
Rebuild a classic exercise you've already written once in a new language, using the staged structure to focus on syntax differences one piece at a time.
Discover more prompts that could help with your workflow.
Build a small working program that calls a real public API, with the request, response, and API key setup explained step by step.
Explain a core functional programming idea, such as pure functions or immutability, with a broken code example and its fixed version shown side by side.
Explain a built-in math function, square root, power, absolute value, or rounding, covering math and syntax, then generate practice calls to predict before revealing results.
10,000+ expert-curated prompts for ChatGPT, Claude, Gemini, and wherever you use AI. Our extension helps any prompt deliver better results.